<html>
<head>
<style><!--
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
font-size: 10pt;
font-family:Verdana
}
--></style>
</head>
<body class='hmmessage'>
Hi Marks,<br><br> Thanks for pointing out possible problems with our system. I will talk to the <br>system admin about these issues.<br><br>Fhokrul<br><br><br><br>> Date: Fri, 29 Jan 2010 09:47:53 -0600<br>> From: L-marks@northwestern.edu<br>> To: wien@zeus.theochem.tuwien.ac.at<br>> Subject: [Wien] Fwd: MPI segmentation fault<br>> <br>> I've edited your information down (too large for the list), and am<br>> including it so others can see if they run into similar problems.<br>> <br>> In essence, you have a mess and you are going to have to talk to your<br>> sysadmin (hikmpn) to get things sorted out. Issues:<br>> <br>> a) You have openmpi-1.3.3. This works for small problems, fails for<br>> large ones. This needs to be updated to 1.4.0 or 1.4.1 (the older<br>> versions of openmpi have bugs).<br>> b) The openmpi was compiled with ifort 10.1 but you are using 11.1.064<br>> for Wien2k -- could lead to problems.<br>> c) The openmpi was compiled with gcc and ifort 10.1, not icc and ifort<br>> which could lead to problems.<br>> d) The fftw library you are using was compiled with gcc not icc, this<br>> could lead to problems.<br>> e) Some of the shared libraries are in your LD_LIBRARY_PATH, you will<br>> need to add -x LD_LIBRARY_PATH to how mpirun is called (in<br>> $WIENROOT/parallel_options) -- look at man mpirun.<br>> f) I still don't know what the stack limits are on your machine --<br>> this can lead to severe problems in lapw0_mpi<br>> <br>> ---------- Forwarded message ----------<br>> From: Fhokrul Islam <fhokrul.islam@lnu.se><br>> Date: Fri, Jan 29, 2010 at 9:16 AM<br>> Subject: MPI segmentation fault<br>> To: "L-marks@northwestern.edu" <L-marks@northwestern.edu><br>> <br>> Below are the information that you requested. I would like to mention<br>> that MPI worked fine when I used it for a bulk<br>> 8 atom system. But for surface supercell of 96 atom it crashes at lapw0.<br>> <br>> Thanks,<br>> Fhokrul<br>> <br>> >> 1) Please do "ompi_info " and paste the output to the end of your<br>> >> response to this email.<br>> <br>> 1. [eishfh@milleotto s110]$ ompi_info<br>> Package: Open MPI hikmpn@milleotto.local Distribution<br>> Open MPI: 1.3.3<br>> Prefix: /home/hikmpn/local<br>> Configured architecture: x86_64-unknown-linux-gnu<br>> Configure host: milleotto.local<br>> Configured by: hikmpn<br>> Fortran90 bindings size: small<br>> C compiler: gcc<br>> C compiler absolute: /usr/bin/gcc<br>> C++ compiler: g++<br>> C++ compiler absolute: /usr/bin/g++<br>> Fortran77 compiler: ifort<br>> Fortran77 compiler abs: /sw/pkg/intel/10.1/bin//ifort<br>> Fortran90 compiler: ifort<br>> Fortran90 compiler abs: /sw/pkg/intel/10.1/bin//ifort<br>> <br>> >> 2) Also paste the output of "echo $LD_LIBRARY_PATH"<br>> <br>> 2. [eishfh@milleotto s110]$ echo $LD_LIBRARY_PATH<br>> /home/eishfh/fftw-2.1.5-gcc/lib/:/home/hikmpn/local/lib/:/sw/pkg/intel/11.1.064//lib/intel64:/sw/pkg/mkl/10.0/lib/em64t:/lib64:/usr/lib64:/usr/X11R6/lib64:/lib:/usr/lib:/usr/X11R6/lib:/usr/local/lib<br>> <br>> >> 3) If you have in your .bashrc a "ulimit -s unlimited" please edit<br>> >> this (temporarily) out, then ssh into one of the child nodes.<br>> <br>> After editing .bashrc file I did the following from the child node:<br>> <br>> 3. [eishfh@mn012 ~]$ which mpirun<br>> /home/hikmpn/local/bin/mpirun<br>> <br>> 4. [eishfh@mn012 ~]$ which lapw0_mpi<br>> /disk/global/home/eishfh/Wien2k_09_2/lapw0_mpi<br>> <br>> 5. [eishfh@mn012 ~]$ echo $LD_LIBRARY_PATH<br>> -bash: home/eishfh/fftw-2.1.5-gcc/lib/:/home/hikmpn/local/lib/:/sw/pkg/intel/11.1.064//lib/intel64:/sw/pkg/mkl/10.0/lib/em64t:/lib64:/usr/lib64:/usr/X11R6/lib64:/lib:/usr/lib:/usr/X11R6/lib:/usr/local/lib<br>> <br>> 6. [eishfh@mn012 ~]$ ldd $WIENROOT/lapw0_mpi<br>> libmkl_intel_lp64.so =><br>> /sw/pkg/mkl/10.0/lib/em64t/libmkl_intel_lp64.so (0x00002ab5610d3000)<br>> libmkl_sequential.so =><br>> /sw/pkg/mkl/10.0/lib/em64t/libmkl_sequential.so (0x00002ab5613d9000)<br>> libmkl_core.so => /sw/pkg/mkl/10.0/lib/em64t/libmkl_core.so<br>> (0x00002ab561566000)<br>> libiomp5.so => /sw/pkg/intel/11.1.064//lib/intel64/libiomp5.so<br>> (0x00002ab561738000)<br>> libsvml.so => /sw/pkg/intel/11.1.064//lib/intel64/libsvml.so<br>> (0x00002ab5618e9000)<br>> libimf.so => /sw/pkg/intel/11.1.064//lib/intel64/libimf.so<br>> (0x00002ab562694000)<br>> libifport.so.5 =><br>> /sw/pkg/intel/11.1.064//lib/intel64/libifport.so.5<br>> (0x00002ab562a28000)<br>> libifcoremt.so.5 =><br>> /sw/pkg/intel/11.1.064//lib/intel64/libifcoremt.so.5<br>> (0x00002ab562b61000)<br>> libintlc.so.5 =><br>> /sw/pkg/intel/11.1.064//lib/intel64/libintlc.so.5 (0x00002ab562e05000)<br>> <br>> -- <br>> Laurence Marks<br>> Department of Materials Science and Engineering<br>> MSE Rm 2036 Cook Hall<br>> 2220 N Campus Drive<br>> Northwestern University<br>> Evanston, IL 60208, USA<br>> Tel: (847) 491-3996 Fax: (847) 491-7820<br>> email: L-marks at northwestern dot edu<br>> Web: www.numis.northwestern.edu<br>> Chair, Commission on Electron Crystallography of IUCR<br>> www.numis.northwestern.edu/<br>> Electron crystallography is the branch of science that uses electron<br>> scattering and imaging to study the structure of matter.<br>> _______________________________________________<br>> Wien mailing list<br>> Wien@zeus.theochem.tuwien.ac.at<br>> http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien<br> <br /><hr />Your E-mail and More On-the-Go. Get Windows Live Hotmail Free. <a href='https://signup.live.com/signup.aspx?id=60969' target='_new'>Sign up now.</a></body>
</html>